Model comparison
Granite 3.1 8b Instruct vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
MiniMaxSummary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 1 category and MiniMax-M2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2 leads 53.0 to 35.5.
Side by side
| Granite 3.1 8b Instruct | MiniMax-M2 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 32.4 | 37.4 |
| Released | — | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 13 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Granite 3.1 8b Instruct: 34.5 (#233), MiniMax-M2: 39.3 (#159)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1186 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
Agentic & Tool Use Too close to call
Granite 3.1 8b Instruct: 24.1 (#120), MiniMax-M2: 25.1 (#109)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Berkeley Function Calling Leaderboard | 27.1% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 22.1 (#207), MiniMax-M2: 19.4 (#258)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
Math MiniMax-M2 leads
Granite 3.1 8b Instruct: 33.0 (#209), MiniMax-M2: 37.3 (#160)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1152 | 1352 |
Knowledge MiniMax-M2 leads
Granite 3.1 8b Instruct: 31.1 (#220), MiniMax-M2: 37.0 (#163)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1142 | 1337 |
Multilingual MiniMax-M2 leads
Granite 3.1 8b Instruct: 30.9 (#260), MiniMax-M2: 45.3 (#171)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1099 | 1313 |
| LMArena Chinese | 1145 | 1366 |
| LMArena Russian | 1092 | 1331 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Spanish | — | 1326 |
Instruction Following MiniMax-M2 leads
Granite 3.1 8b Instruct: 58.6 (#259), MiniMax-M2: 70.2 (#166)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1131 | 1328 |
Long Context MiniMax-M2 leads
Granite 3.1 8b Instruct: 35.2 (#241), MiniMax-M2: 40.5 (#153)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1162 | 1331 |
Writing & Preference MiniMax-M2 leads
Granite 3.1 8b Instruct: 35.5 (#266), MiniMax-M2: 53.0 (#162)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1150 | 1340 |
| LMArena Creative Writing | 1129 | 1286 |
| LMArena Multi-Turn | 1108 | 1361 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and MiniMax-M2 share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and MiniMax-M2 has 21.